| OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning | May 28, 2024 | MMLU | CodeCode Available | 1 |
| Efficient multi-prompt evaluation of LLMs | May 27, 2024 | MMLU | CodeCode Available | 7 |
| GECKO: Generative Language Model for English, Code and Korean | May 24, 2024 | kmmluLanguage Modeling | —Unverified | 0 |
| Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training | May 23, 2024 | GSM8KMixture-of-Experts | CodeCode Available | 7 |
| Instruction Tuning With Loss Over Instructions | May 23, 2024 | HumanEvalMMLU | CodeCode Available | 1 |
| An Assessment of Model-On-Model Deception | May 10, 2024 | MMLUmodel | —Unverified | 0 |
| SUTRA: Scalable Multilingual Language Model Architecture | May 7, 2024 | Computational EfficiencyHallucination | —Unverified | 0 |
| Octopus v4: Graph of language models | Apr 30, 2024 | MMLU | —Unverified | 0 |
| LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding | Apr 25, 2024 | GSM8KHellaSwag | CodeCode Available | 3 |
| Make Your LLM Fully Utilize the Context | Apr 25, 2024 | 4kInformation Retrieval | CodeCode Available | 5 |
